• Journal of information and communication convergence engineering
• /
• v.15 no.2
• /
• pp.85-90
• /
• 2017

Expert systems for health diagnosis are only for medical experts who have deep knowledge in the field but we need a self-checking pre-diagnosis system for preventive public health monitoring. Korea Traditional Medicine is popular in use among Korean public but there exist few available health information systems on the internet. A computerized self-checking diagnosis system is proposed to reduce the social cost by monitoring health status with simple symptom checking procedures especially for Korea Traditional Medicine users. Based on the national reports for disease/symptoms of Korea Traditional Medicine, we build a reliable database and devise an intelligent inference engine using fuzzy c-means clustering. The implemented system gives five most probable diseases a user might have with respect to symptoms given by the user. Inference results are verified by Korea Traditional Medicine doctors as sufficiently accurate and easy to use.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.6
• /
• pp.1230-1237
• /
• 2009

In this paper, we develop a design methodology of Granular-based Radial Basis Function Neural Networks(GRBFNN) by context-based clustering. In contrast with the plethora of existing approaches, here we promote a development strategy in which a topology of the network is predominantly based upon a collection of information granules formed on a basis of available experimental data. The output space is granulated making use of the K-Means clustering while the input space is clustered with the aid of a so-called context-based fuzzy clustering. The number of information granules produced for each context is adjusted so that we satisfy a certain reconstructability criterion that helps us minimize an error between the original data and the ones resulting from their reconstruction involving prototypes of the clusters and the corresponding membership values. In contrast to "standard" Radial Basis Function neural networks, the output neuron of the network exhibits a certain functional nature as its connections are realized as local linear whose location is determined by the values of the context and the prototypes in the input space. The other parameters of these local functions are subject to further parametric optimization. Numeric examples involve some low dimensional synthetic data and selected data coming from the Machine Learning repository.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.2
• /
• pp.397-406
• /
• 2000

Genetic algorithm is used as a means of search, optimization md machine learning, its structure is simple but it is applied to various areas. And it is about an active and effective controller which can flexibly prepare for changeable circumstances. For this study, research about an action base system evolving by itself is also being considered. There is to have a problem that depended entirely on heuristic knowledge of expert forming membership function and control rule for fuzzy controller design. In this paper, for forming the fuzzy control to perform self-organization, we tuned the membership function to the most optimal using a genetic algorithm(GA) and improved the control efficiency by the self-correction and generation of control rules.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.4
• /
• pp.246-253
• /
• 2016

Infrared (IR) imaging has been researched for various applications such as surveillance. IR radiation has the capability to detect thermal characteristics of objects under low-light conditions. However, automatic segmentation for finding the object of interest would be challenging since the IR detector often provides the low spatial and contrast resolution image without color and texture information. Another hindrance is that the image can be degraded by noise and clutters. This paper proposes multi-level segmentation for extracting regions of interest (ROIs) and objects of interest (OOIs) in the IR scene. Each level of the multi-level segmentation is composed of a k-means clustering algorithm, an expectation-maximization (EM) algorithm, and a decision process. The k-means clustering initializes the parameters of the Gaussian mixture model (GMM), and the EM algorithm estimates those parameters iteratively. During the multi-level segmentation, the area extracted at one level becomes the input to the next level segmentation. Thus, the segmentation is consecutively performed narrowing the area to be processed. The foreground objects are individually extracted from the final ROI windows. In the experiments, the effectiveness of the proposed method is demonstrated using several IR images, in which human subjects are captured at a long distance. The average probability of error is shown to be lower than that obtained from other conventional methods such as Gonzalez, Otsu, k-means, and EM methods.

• Safety and Health at Work
• /
• v.7 no.4
• /
• pp.307-316
• /
• 2016

Background: Resilience engineering (RE) is a new paradigm that can control incidents and reduce their consequences. Integrated RE includes four new factors-self-organization, teamwork, redundancy, and fault-tolerance-in addition to conventional RE factors. This study aimed to evaluate the impacts of these four factors on RE and determine the most efficient factor in an uncertain environment. Methods: The required data were collected through a questionnaire in a petrochemical plant in June 2013. The questionnaire was completed by 115 respondents including 37 managers and 78 operators. Fuzzy data envelopment analysis was used in different ${\alpha}$-cuts in order to calculate the impact of each factor. Analysis of variance was employed to compare the efficiency score means of the four abovementioned factors. Results: The results showed that as ${\alpha}$ approached 0 and the system became fuzzier (${\alpha}=0.3$ and ${\alpha}=0.1$), teamwork played a significant role and had the highest impact on the resilient system. In contrast, as ${\alpha}$ approached 1 and the fuzzy system went toward a certain mode (${\alpha}=0.9$ and ${\alpha}=1$), redundancy had a vital role in the selected resilient system. Therefore, redundancy and teamwork were the most efficient factors. Conclusion: The approach developed in this study could be used for identifying the most important factors in such environments. The results of this study may help managers to have better understanding of weak and strong points in such industries.

• ETRI Journal
• /
• v.36 no.3
• /
• pp.333-342
• /
• 2014

Most hyper-ellipsoidal clustering (HEC) approaches use the Mahalanobis distance as a distance metric. It has been proven that HEC, under this condition, cannot be realized since the cost function of partitional clustering is a constant. We demonstrate that HEC with a modified Gaussian kernel metric can be interpreted as a problem of finding condensed ellipsoidal clusters (with respect to the volumes and densities of the clusters) and propose a practical HEC algorithm that is able to efficiently handle clusters that are ellipsoidal in shape and that are of different size and density. We then try to refine the HEC algorithm by utilizing ellipsoids defined on the kernel feature space to deal with more complex-shaped clusters. The proposed methods lead to a significant improvement in the clustering results over K-means algorithm, fuzzy C-means algorithm, GMM-EM algorithm, and HEC algorithm based on minimum-volume ellipsoids using Mahalanobis distance.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1958-1959
• /
• 2011

RBFNNs(Radial Basis Function Neural Networks) 모델의 경우 Min-Max, HCM(Hard C-means)클러스터링 그리고 FCM(Fuzzy C-means)클러스터링 중 한가지를 통해 데이터 입자는 로드 규칙을 생성한 후 퍼지 공간을 분할 및 가우시안 함수의 정점을 정의한다. 본 논문은 기존의 방법과는 다르게 Min-Max와 FCM클러스터링을 혼합하여 로드의 규칙을 생성한 후 퍼지 공간을 분할 및 가우시안 함수의 정정을 정의하는 방법으로 사용하고자 한다. PSO최적화 알고리즘을 이용하여 같은조건에서 최적화한 기존의 방법으로 모델링된 RBFNNs와 Min-Max와 FCM 클러스터링을 혼합하여 사용한 방법의 비교를 통하여 어떤 모델의 성능이 더욱 좋은지 비교하고자 한다.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.4
• /
• pp.1910-1914
• /
• 2015

Human posture recognition is an attractive and challenging topic in computer vision due to its promising applications in the areas of personal health care, environmental awareness, human-computer-interaction and surveillance systems. Human posture recognition in video sequences consists of two stages: the first stage is training and evaluation and the second is deployment. In the first stage, the system is trained and evaluated using datasets of human postures to ‘teach’ the system to classify human postures for any future inputs. When the training and evaluation process is deemed satisfactory as measured by recognition rates, the trained system is then deployed to recognize human postures in any input video sequence. Different classifiers were used in the training such as Multilayer Perceptron Feedforward Neural networks, Self-Organizing Maps, Fuzzy C Means and K Means. Results show that supervised learning classifiers tend to perform better than unsupervised classifiers for the case of human posture recognition.

• Journal of Industrial Technology
• /
• v.29 no.B
• /
• pp.9-15
• /
• 2009

In the case of traditional binary encoding technique, it takes long time to converge the optimal solutions and brings about complexity of the systems due to encoding and decoding procedures. However, the ROGAs (real-coded genetic algorithms) do not require these procedures, and the k-means clustering algorithm can avoid global searching space. Thus, this paper proposes a new approach by using their advantages. The proposed method constructs the multiple predictors using the optimal differences that can reveal the patterns better and properties concealed in non-stationary time series where the k-means clustering algorithm is used for data classification to each predictor, then selects the best predictor. After selecting the best predictor, the cluster centers of the predictor are tuned finely via RCGKA in secondary tuning procedure. Therefore, performance of the predictor can be more enhanced. Finally, we verifies the prediction performance of the proposed system via simulating typical time series examples.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.6
• /
• pp.146-153
• /
• 2010

For the indoor location, wireless fingerprinting is most favorable because fingerprinting is most accurate among the technique for wireless network based indoor location which does not require any special equipments dedicated for positioning. As fingerprinting method,k-nearest neighbor(KNN) has been widely applied for indoor location in wireless location area networks(WLAN), but its performance is sensitive to number of neighborsk and positions of reference points(RPs). So possibilistic fuzzy c-means(PFCM) clustering algorithm is applied to improve KNN, which is the KNN/PFCM hybrid algorithm presented in this paper. In the proposed algorithm, through KNN,k RPs are firstly chosen as the data samples of PFCM based on signal to noise ratio(SNR). Then, thek RPs are classified into different clusters through PFCM based on SNR. Experimental results indicate that the proposed KNN/PFCM hybrid algorithm generally outperforms KNN and KNN/FCM algorithm when the locations error is less than 2m.